M
Massimo Cossentino
Researcher at Indian Council of Agricultural Research
Publications - 162
Citations - 2951
Massimo Cossentino is an academic researcher from Indian Council of Agricultural Research. The author has contributed to research in topics: Multi-agent system & Design process. The author has an hindex of 29, co-authored 158 publications receiving 2854 citations. Previous affiliations of Massimo Cossentino include National Research Council & University of Palermo.
Papers
More filters
BookDOI
Multi-Agent Systems
TL;DR: A novel transfer learning technique to autonomously construct an inter-task mapping by using a novel combinations of sparse coding, sparse projection learning, and sparse pseudo-input gaussian processes to improve the performance of a learned policy on a fixed number of samples.
Book ChapterDOI
From Requirements to Code with PASSI Methodology
TL;DR: A Process for Agent Societies Specification and Implementation (PASSI) is a step-by-step requirement-to-code methodology for designing and developing multi-agent societies, integrating design models and concepts from both object-oriented software engineering and artificial intelligence approaches using the UML notation.
Journal ArticleDOI
ASPECS: an agent-oriented software process for engineering complex systems
TL;DR: This paper introduces an agent-oriented software process for engineering complex systems called ASPECS, based on a holonic organisational metamodel and provides a step-by-step guide from requirements to code allowing the modelling of a system at different levels of details using a set of refinement methods.
Journal Article
A study of some multi-agent meta-models
TL;DR: In this paper, a unified meta-model is proposed as a first step toward interoperability between agent-oriented methodologies, such as ADELFE, Gaia and PASSI, by comparing a certain number of features at the agent or system level.
Journal ArticleDOI
Process models for agent-based development
TL;DR: This paper focuses on process models for software development and puts these in relation with current researches in AOSE, and surveys the characteristics of a number of agent-oriented methodologies, as they pertain to software processes.